Retrieval & data
Grounding
Definition
Grounding means tying model output to verifiable sources — retrieved documents, search results, or database records — rather than relying on parametric memory. Grounded answers can be checked.
An ungrounded answer comes from whatever the model absorbed during training, with no way to verify it. A grounded answer comes with citations you can follow.
Grounding is the main defence against hallucination in production systems. The pattern is: retrieve relevant sources, instruct the model to answer only from them, and require a citation for each claim. Then a reviewer can spot-check.
Grounding is not automatic once you add retrieval. Models will still blend parametric knowledge with retrieved context unless explicitly instructed not to, which produces answers that look sourced but are not.
Related terms
RAG (Retrieval-Augmented Generation)
RAG retrieves relevant passages from your own documents and inserts them into the prompt before the model answers. It grounds responses in your data, cuts hallucination, and needs no retraining.
Hallucination
A hallucination is model output that is fluent and confident but factually wrong — invented citations, non-existent functions, fabricated statistics. It stems from models being trained to produce plausible text, not verified truth.
Knowledge cutoff
A model's knowledge cutoff is the date after which it has no training data. It cannot know about events, releases or prices after that point unless given the information in the prompt or via search.
Citation
A citation links a model claim to the source it came from. Real citations come from grounding in retrieved documents; models asked to cite from memory frequently invent plausible-looking references.
Embedding
An embedding is a list of numbers representing the meaning of a piece of text, such that semantically similar texts have mathematically similar vectors. Embeddings make meaning-based search possible.
Vector database
A vector database stores embeddings and finds the most similar ones to a query vector quickly. It is the retrieval layer of most RAG systems. Examples include Pinecone, Weaviate, Qdrant and pgvector.
Put this into practice
Understanding the term is step one. Our free courses and tools let you actually use it.